Credit Card Fraud Detection Using Fuzzy Rough Nearest Neighbor and Sequential Minimal Optimization with Logistic Regression

<p>The global online communication channel made possible with the internet has increased credit card fraud leading to huge loss of monetary fund in their billions annually for consumers and financial institutions. The fraudsters constantly devise new strategy perpetrate illegal transactions. As such, innovative detection systems combating are imperative curb these losses. This paper presents combination multiple classifiers through stacking ensemble technique detection. fuzzy-rough nearest neighbor (FRNN) sequential minimal optimization (SMO) employed as base classifiers. Their combined prediction becomes data input meta-classifier, which is logistic regression (LR) resulting a final predictive outcome improved Simulation results compared seven other algorithms affirms that model can adequately detect rates 84.90% 76.30%.</p>